Finding Pulsars in Real-Time

Research output: Contribution to ConferencePaperOther research output

Abstract

Finding new pulsars has always been a challenging problem, but this challenge is nowadays exacerbated by the increasing data rates of modern radio telescopes. Because of these increased data rates, traditional approaches to searching, based on storing data for off-line processing, are becoming unfeasible. Therefore, we propose a new pulsar searching pipeline that, by exploiting high-performance computing techniques, is able to process observational data in real-time. To achieve the real-time goal we parallelized all the steps of the pipeline to run on many-core accelerators, and used auto-tuning to adapt and optimize the pipeline for different platforms, telescopes, and searching parameters. In this paper, we test our pipeline on three different platforms: two Graphics Processing Units from AMD and NVIDIA, and an Intel Xeon Phi. Furthermore, we test it on three different scenarios, based on the operational parameters of three state-of-the-art telescopes. Results show that our pipeline can adapt to all tested platforms and scenarios, and achieves real-time performance and linear scalability. Because power consumption is a main concern for radio telescopes, and will be the main bottleneck for the construction of the Square Kilometer Array, we also measure the power consumed by our pipeline. By comparing the results obtained on many-core accelerators with the results obtained using a traditional multi-core CPU, we conclude that the accelerators can provide up to a factor 8 improvement in execution time, and up to a factor 6 reduction in power consumption.

Conference

Conference1th IEEE International Conference on eScience
Period31/08/154/09/15

Fingerprint

Pipelines
Particle accelerators
Radio telescopes
Telescopes
Electric power utilization
Program processors
Pulsars
Scalability
Tuning
Processing

Cite this

Sclocco, A., Bal, H. E., & van Nieuwpoort, R. V. (2015). Finding Pulsars in Real-Time. Paper presented at 1th IEEE International Conference on eScience, . https://doi.org/10.1109/eScience.2015.11
Sclocco, A. ; Bal, H.E. ; van Nieuwpoort, R.V. / Finding Pulsars in Real-Time. Paper presented at 1th IEEE International Conference on eScience, .
@conference{7ccbb4ca782b4b8bb7cb2438303ef266,
title = "Finding Pulsars in Real-Time",
abstract = "Finding new pulsars has always been a challenging problem, but this challenge is nowadays exacerbated by the increasing data rates of modern radio telescopes. Because of these increased data rates, traditional approaches to searching, based on storing data for off-line processing, are becoming unfeasible. Therefore, we propose a new pulsar searching pipeline that, by exploiting high-performance computing techniques, is able to process observational data in real-time. To achieve the real-time goal we parallelized all the steps of the pipeline to run on many-core accelerators, and used auto-tuning to adapt and optimize the pipeline for different platforms, telescopes, and searching parameters. In this paper, we test our pipeline on three different platforms: two Graphics Processing Units from AMD and NVIDIA, and an Intel Xeon Phi. Furthermore, we test it on three different scenarios, based on the operational parameters of three state-of-the-art telescopes. Results show that our pipeline can adapt to all tested platforms and scenarios, and achieves real-time performance and linear scalability. Because power consumption is a main concern for radio telescopes, and will be the main bottleneck for the construction of the Square Kilometer Array, we also measure the power consumed by our pipeline. By comparing the results obtained on many-core accelerators with the results obtained using a traditional multi-core CPU, we conclude that the accelerators can provide up to a factor 8 improvement in execution time, and up to a factor 6 reduction in power consumption.",
author = "A. Sclocco and H.E. Bal and {van Nieuwpoort}, R.V.",
year = "2015",
doi = "10.1109/eScience.2015.11",
language = "English",
note = "1th IEEE International Conference on eScience ; Conference date: 31-08-2015 Through 04-09-2015",

}

Sclocco, A, Bal, HE & van Nieuwpoort, RV 2015, 'Finding Pulsars in Real-Time' Paper presented at 1th IEEE International Conference on eScience, 31/08/15 - 4/09/15, . https://doi.org/10.1109/eScience.2015.11

Finding Pulsars in Real-Time. / Sclocco, A.; Bal, H.E.; van Nieuwpoort, R.V.

2015. Paper presented at 1th IEEE International Conference on eScience, .

Research output: Contribution to ConferencePaperOther research output

TY - CONF

T1 - Finding Pulsars in Real-Time

AU - Sclocco, A.

AU - Bal, H.E.

AU - van Nieuwpoort, R.V.

PY - 2015

Y1 - 2015

N2 - Finding new pulsars has always been a challenging problem, but this challenge is nowadays exacerbated by the increasing data rates of modern radio telescopes. Because of these increased data rates, traditional approaches to searching, based on storing data for off-line processing, are becoming unfeasible. Therefore, we propose a new pulsar searching pipeline that, by exploiting high-performance computing techniques, is able to process observational data in real-time. To achieve the real-time goal we parallelized all the steps of the pipeline to run on many-core accelerators, and used auto-tuning to adapt and optimize the pipeline for different platforms, telescopes, and searching parameters. In this paper, we test our pipeline on three different platforms: two Graphics Processing Units from AMD and NVIDIA, and an Intel Xeon Phi. Furthermore, we test it on three different scenarios, based on the operational parameters of three state-of-the-art telescopes. Results show that our pipeline can adapt to all tested platforms and scenarios, and achieves real-time performance and linear scalability. Because power consumption is a main concern for radio telescopes, and will be the main bottleneck for the construction of the Square Kilometer Array, we also measure the power consumed by our pipeline. By comparing the results obtained on many-core accelerators with the results obtained using a traditional multi-core CPU, we conclude that the accelerators can provide up to a factor 8 improvement in execution time, and up to a factor 6 reduction in power consumption.

AB - Finding new pulsars has always been a challenging problem, but this challenge is nowadays exacerbated by the increasing data rates of modern radio telescopes. Because of these increased data rates, traditional approaches to searching, based on storing data for off-line processing, are becoming unfeasible. Therefore, we propose a new pulsar searching pipeline that, by exploiting high-performance computing techniques, is able to process observational data in real-time. To achieve the real-time goal we parallelized all the steps of the pipeline to run on many-core accelerators, and used auto-tuning to adapt and optimize the pipeline for different platforms, telescopes, and searching parameters. In this paper, we test our pipeline on three different platforms: two Graphics Processing Units from AMD and NVIDIA, and an Intel Xeon Phi. Furthermore, we test it on three different scenarios, based on the operational parameters of three state-of-the-art telescopes. Results show that our pipeline can adapt to all tested platforms and scenarios, and achieves real-time performance and linear scalability. Because power consumption is a main concern for radio telescopes, and will be the main bottleneck for the construction of the Square Kilometer Array, we also measure the power consumed by our pipeline. By comparing the results obtained on many-core accelerators with the results obtained using a traditional multi-core CPU, we conclude that the accelerators can provide up to a factor 8 improvement in execution time, and up to a factor 6 reduction in power consumption.

U2 - 10.1109/eScience.2015.11

DO - 10.1109/eScience.2015.11

M3 - Paper

ER -

Sclocco A, Bal HE, van Nieuwpoort RV. Finding Pulsars in Real-Time. 2015. Paper presented at 1th IEEE International Conference on eScience, . https://doi.org/10.1109/eScience.2015.11